audit_preview

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden, and it does disclose the key behavioral contract: blank/static previews are rejected and motion/duration/occupancy are compared. It does not state what the result of a failed audit looks like, whether it mutates or blocks any state, or any permission requirements, so significant gaps remain.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single front-loaded sentence with the reject condition first and the comparison second; no filler. It is slightly dense and could have used a clause to route against siblings, but every word earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a two-parameter validation tool with no output schema and no annotations, the description covers the core purpose and the optional reference reasonably well. It leaves the failure/output behavior and the required parameter's format undocumented, which is the main missing piece.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It does clarify that the reference GIF is an optional 'art-direction reference', which explains the reference_gif parameter and its empty default, but it says nothing about the required preview_gif or expected format beyond naming the checks.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific action ('reject blank/static previews') on a specific resource (the preview GIF) and enumerates the checks it performs: duration, motion, occupancy. An agent can tell this is a preview-quality gate, though it doesn't explicitly contrast itself with the nearby validate_motion / validate_output siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The phrase 'before a delivery is accepted' implies usage timing, so an agent can infer this is a final gate step. However, no alternatives are named and there is no guidance on when to prefer this over validate_output, preview, or validate_motion, which is a real gap given how many similar siblings exist.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.